Commits · 6cd5e5b07e4415d064d93b8a66331a097bd9287e · OpenDAS / vllm_cscc · GitLab

10 Sep, 2024 1 commit
- [Misc] Fused MoE Marlin support for GPTQ (#8217) · 6cd5e5b0
  Dipika Sikka authored Sep 09, 2024
  
  6cd5e5b0
09 Sep, 2024 2 commits
- [Misc] GPTQ Activation Ordering (#8135) · c7cb5c33
  Kyle Sayers authored Sep 09, 2024
  
  c7cb5c33
- [Bugfix] Correct adapter usage for cohere and jamba (#8292) · f9b4a2d4
  Vladislav Kruglikov authored Sep 09, 2024
  
  f9b4a2d4
07 Sep, 2024 4 commits
- [Model][VLM] Decouple weight loading logic for `Paligemma` (#8269) · 36bf8150
  Isotr0py authored Sep 08, 2024
  
  36bf8150
- [Model][VLM] Support multi-images inputs for InternVL2 models (#8201) · e8071259
  Isotr0py authored Sep 07, 2024
  
  e8071259
- [Bugfix] Fix broken OpenAI tensorizer test (#8258) · 9f68e00d
  Cyrus Leung authored Sep 07, 2024
  
  9f68e00d
- [Model] Multi-input support for LLaVA (#8238) · 2f707fcb
  Cyrus Leung authored Sep 07, 2024
  
  2f707fcb
06 Sep, 2024 3 commits
- [Model] Allow loading from original Mistral format (#8168) · 29f49cd6
  Patrick von Platen authored Sep 07, 2024
```
Co-authored-by: Michael Goin <michael@neuralmagic.com>
```
  29f49cd6
- [Misc] Remove `SqueezeLLM` (#8220) · 23f32229
  Dipika Sikka authored Sep 06, 2024
  
  23f32229
- [Kernel] [Triton] Memory optimization for awq_gemm and awq_dequantize, 2x throughput (#8248) · 9db52eab
  rasmith authored Sep 06, 2024
  
  9db52eab
05 Sep, 2024 4 commits
- Move verify_marlin_supported to GPTQMarlinLinearMethod (#8165) · 2ee45281
  Michael Goin authored Sep 05, 2024
  
  2ee45281
- [MODEL] Qwen Multimodal Support (Qwen-VL / Qwen-VL-Chat) (#8029) · 9da25a88
  Alex Brooks authored Sep 05, 2024
```
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  9da25a88
- Inclusion of InternVLChatModel In PP_SUPPORTED_MODELS(Pipeline Parallelism) (#7860) · 8685ba1a
  manikandan.tm@zucisystems.com authored Sep 05, 2024
  
  8685ba1a
- [Misc] Clean up RoPE forward_native (#8076) · 4624d98d
  Woosuk Kwon authored Sep 04, 2024
  
  4624d98d
04 Sep, 2024 5 commits
- [Neuron] Adding support for adding/ overriding neuron configuration a… (#8062) · 008cf886
  Harsha vardhan manoj Bikki authored Sep 04, 2024
```
Co-authored-by: Harsha Bikki <harbikh@amazon.com>
```
  008cf886
- [Feature] OpenAI-Compatible Tools API + Streaming for Hermes & Mistral models (#5649) · e02ce498
  Kyle Mistele authored Sep 04, 2024
```
Co-authored-by: constellate <constellate@1-ai-appserver-staging.codereach.com>
Co-authored-by: Kyle Mistele <kyle@constellate.ai>
```
  e02ce498
- [Bugfix] remove post_layernorm in siglip (#8106) · d3311562
  wnma authored Sep 04, 2024
  
  d3311562
- [Model] Add Ultravox support for multiple audio chunks (#7963) · 2be8ec6e
  Peter Salas authored Sep 03, 2024
  
  2be8ec6e
- [Misc] Update fbgemmfp8 to use `vLLMParameters` (#7972) · e16fa99a
  Dipika Sikka authored Sep 03, 2024
```
Co-authored-by: Michael Goin <michael@neuralmagic.com>
```
  e16fa99a
03 Sep, 2024 2 commits
- [Misc] Update `GPTQ` to use `vLLMParameters` (#7976) · 2188a60c
  Dipika Sikka authored Sep 03, 2024
  
  2188a60c
- [Bugfix][VLM] Add fallback to SDPA for ViT model running on CPU backend (#8061) · ec266536
  Isotr0py authored Sep 03, 2024
  
  ec266536
02 Sep, 2024 3 commits
- [Bugfix] Fix internlm2 tensor parallel inference (#8055) · dd2a6a82
  Isotr0py authored Sep 02, 2024
  
  dd2a6a82
- [SpecDecode][Kernel] Flashinfer Rejection Sampling (#7244) · e6a26ed0
  Lily Liu authored Sep 01, 2024
  
  e6a26ed0
- [Model] Add Granite model (#7436) · f8d60145
  Shawn Tan authored Sep 01, 2024
```
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
```
  f8d60145
01 Sep, 2024 1 commit
- [Misc] Optional installation of audio related packages (#8063) · 5b86b199
  Roger Wang authored Sep 01, 2024
  
  5b86b199
31 Aug, 2024 1 commit
- [Bugfix] Fix import error in Phi-3.5-MoE (#8052) · d05f0a9d
  Cyrus Leung authored Aug 31, 2024
  
  d05f0a9d
30 Aug, 2024 5 commits
- [Model] Adding support for MSFT Phi-3.5-MoE (#7729) · 1248e850
  Wenxiang authored Aug 31, 2024
```
Co-authored-by: Your Name <you@example.com>
Co-authored-by: Zeqi Lin <zelin@microsoft.com>
Co-authored-by: Zeqi Lin <Zeqi.Lin@microsoft.com>
```
  1248e850
- [VLM][Model] TP support for ViTs (#7186) · f97be32d
  Jungho Christopher Cho authored Aug 31, 2024
```
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
```
  f97be32d
- [Bugfix] Fix import error in Exaone model (#8034) · afd39a45
  Cyrus Leung authored Aug 30, 2024
  
  afd39a45
- [MODEL] add Exaone model support (#7819) · dc13e993
  Yohan Na authored Aug 30, 2024
  
  dc13e993
- [Core] Logprobs support in Multi-step (#7652) · 428dd144
  afeldman-nm authored Aug 29, 2024
  
  428dd144
29 Aug, 2024 5 commits
- support bitsandbytes 8-bit and FP4 quantized models (#7445) · 4664ceaa
  chenqianfzh authored Aug 29, 2024
  
  4664ceaa
- [Neuron] Adding support for context-lenght, token-gen buckets. (#7885) · 257afc37
  Harsha vardhan manoj Bikki authored Aug 29, 2024
```
Co-authored-by: Harsha Bikki <harbikh@amazon.com>
```
  257afc37
- [misc] update tpu int8 to use new vLLM Parameters (#7973) · 86a677de
  Dipika Sikka authored Aug 29, 2024
  
  86a677de
- [Bugfix] Fix incorrect vocal embedding shards for GGUF model in tensor parallelism (#7954) · d78789ac
  Isotr0py authored Aug 30, 2024
  
  d78789ac
- [VLM][Core] Fix exceptions on ragged NestedTensors (#7974) · 74d5543e
  Peter Salas authored Aug 28, 2024
  
  74d5543e
28 Aug, 2024 4 commits
- [Kernel/Model] Migrate mamba_ssm and causal_conv1d kernels to vLLM (#7651) · fdd9daaf
  Mor Zusman authored Aug 29, 2024
  
  fdd9daaf
- [Kernel] [Triton] [AMD] Adding Triton implementations awq_dequantize and... · e5697d16
  rasmith authored Aug 28, 2024
```
[Kernel] [Triton] [AMD] Adding Triton implementations awq_dequantize and awq_gemm to support AWQ (#7386)
```
  e5697d16
- [Bugfix][VLM] Fix incompatibility between #7902 and #7230 (#7948) · ef9baee3
  Cyrus Leung authored Aug 28, 2024
  
  ef9baee3
- [Core][VLM] Stack multimodal tensors to represent multiple images within each prompt (#7902) · fab5f53e
  Peter Salas authored Aug 27, 2024
  
  fab5f53e